{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QOYIWFAC6YMZRJEPG4Z4GADSVH","short_pith_number":"pith:QOYIWFAC","schema_version":"1.0","canonical_sha256":"83b08b1402f61998a48f3733c30072a9e067e4897227964b579dcaafc5f02adc","source":{"kind":"arxiv","id":"2606.08157","version":1},"attestation_state":"computed","paper":{"title":"Cross Paraphrastic Invariance Learning for Hallucination Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chao Chen, Dongsheng Hong, Shanshan Lin, Sibo Ju, Sihong Xie, Xiangwen Liao","submitted_at":"2026-06-06T13:13:12Z","abstract_excerpt":"Large language models (LLMs) frequently generate hallucinations, which are unsupported by a source document. To avoid costly LLM-as-evaluator pipelines and the heavy annotation demands of existing classifiers, we propose CPIL (Cross Paraphrastic Invariance Learning), a two-stage Siamese framework that maximizes the utility of existing labeled data. Concretely, CPIL constructs informative training pairs by: (i) generating paraphrastic views of each document-claim example as positives, and explicitly aligning their representations to enforce invariance to surface form; and (ii) mining same-docum"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.08157","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-06T13:13:12Z","cross_cats_sorted":[],"title_canon_sha256":"9afcbb145a3d04269d5e82c68f5a6b16da8b1e48915c0bc713a552fd9e4489e3","abstract_canon_sha256":"4658aefe54ffdbe6666410ebc28abcaa3624c8c2cc851a91881aaa77d3cbe644"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:05:28.493015Z","signature_b64":"c4KvDJBzEDM+th+u2YOYrb1LWls61UL7mSYzVxkLn3wk1mSoWDJY6LJBmWy6YKx/6XXGtoBhpXE57Ewr2hMvBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83b08b1402f61998a48f3733c30072a9e067e4897227964b579dcaafc5f02adc","last_reissued_at":"2026-06-09T01:05:28.492345Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:05:28.492345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cross Paraphrastic Invariance Learning for Hallucination Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chao Chen, Dongsheng Hong, Shanshan Lin, Sibo Ju, Sihong Xie, Xiangwen Liao","submitted_at":"2026-06-06T13:13:12Z","abstract_excerpt":"Large language models (LLMs) frequently generate hallucinations, which are unsupported by a source document. To avoid costly LLM-as-evaluator pipelines and the heavy annotation demands of existing classifiers, we propose CPIL (Cross Paraphrastic Invariance Learning), a two-stage Siamese framework that maximizes the utility of existing labeled data. Concretely, CPIL constructs informative training pairs by: (i) generating paraphrastic views of each document-claim example as positives, and explicitly aligning their representations to enforce invariance to surface form; and (ii) mining same-docum"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08157","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.08157/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.08157","created_at":"2026-06-09T01:05:28.492422+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.08157v1","created_at":"2026-06-09T01:05:28.492422+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08157","created_at":"2026-06-09T01:05:28.492422+00:00"},{"alias_kind":"pith_short_12","alias_value":"QOYIWFAC6YMZ","created_at":"2026-06-09T01:05:28.492422+00:00"},{"alias_kind":"pith_short_16","alias_value":"QOYIWFAC6YMZRJEP","created_at":"2026-06-09T01:05:28.492422+00:00"},{"alias_kind":"pith_short_8","alias_value":"QOYIWFAC","created_at":"2026-06-09T01:05:28.492422+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QOYIWFAC6YMZRJEPG4Z4GADSVH","json":"https://pith.science/pith/QOYIWFAC6YMZRJEPG4Z4GADSVH.json","graph_json":"https://pith.science/api/pith-number/QOYIWFAC6YMZRJEPG4Z4GADSVH/graph.json","events_json":"https://pith.science/api/pith-number/QOYIWFAC6YMZRJEPG4Z4GADSVH/events.json","paper":"https://pith.science/paper/QOYIWFAC"},"agent_actions":{"view_html":"https://pith.science/pith/QOYIWFAC6YMZRJEPG4Z4GADSVH","download_json":"https://pith.science/pith/QOYIWFAC6YMZRJEPG4Z4GADSVH.json","view_paper":"https://pith.science/paper/QOYIWFAC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.08157&json=true","fetch_graph":"https://pith.science/api/pith-number/QOYIWFAC6YMZRJEPG4Z4GADSVH/graph.json","fetch_events":"https://pith.science/api/pith-number/QOYIWFAC6YMZRJEPG4Z4GADSVH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QOYIWFAC6YMZRJEPG4Z4GADSVH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QOYIWFAC6YMZRJEPG4Z4GADSVH/action/storage_attestation","attest_author":"https://pith.science/pith/QOYIWFAC6YMZRJEPG4Z4GADSVH/action/author_attestation","sign_citation":"https://pith.science/pith/QOYIWFAC6YMZRJEPG4Z4GADSVH/action/citation_signature","submit_replication":"https://pith.science/pith/QOYIWFAC6YMZRJEPG4Z4GADSVH/action/replication_record"}},"created_at":"2026-06-09T01:05:28.492422+00:00","updated_at":"2026-06-09T01:05:28.492422+00:00"}